2023 IEEE Information Theory Workshop (ITW)最新文献_第3页

Permutation Invariant Individual Batch Learning 置换不变个体批处理学习

2023 IEEE Information Theory Workshop (ITW) Pub Date : 2023-04-23 DOI: 10.1109/ITW55543.2023.10161673

Yaniv Fogel, M. Feder

{"title":"Permutation Invariant Individual Batch Learning","authors":"Yaniv Fogel, M. Feder","doi":"10.1109/ITW55543.2023.10161673","DOIUrl":"https://doi.org/10.1109/ITW55543.2023.10161673","url":null,"abstract":"This paper considers the individual batch learning problem. Batch learning (in contrast to online) refers to the case where there is a \"batch\" of training data and the goal is to predict a test outcome. Individual learning refers to the case where the data (training and test) is arbitrary, individual. This batch individual setting poses a fundamental issue of defining a plausible criterion for a universal learner since in each experiment there is a single test sample. We propose a permutation invariant criterion that, intuitively, lets the individual training sequence manifest its empirical structure for predicting the test sample. This criterion is essentially a min-max regret, where the regret is based on a leave-one-out approach, minimized over the universal learner and maximized over the outcome sequences (thus agnostic). To show its plausibility, we analyze the criterion and its resulting learner for two cases: Binary Bernoulli and 1-D deterministic barrier. For both cases the regret behaves as O(c/N), N the size of the training and c = 1 for the Bernoulli case and log4 for the 1-D barrier. Interestingly, in the Bernoulli case, the regret in the stochastic setting behaves as O(1/2N) while here, in the individual setting, it has a larger constant.","PeriodicalId":439800,"journal":{"name":"2023 IEEE Information Theory Workshop (ITW)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121379948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The Role of the Alphabet in Network Coding: An Optimization Approach 字母表在网络编码中的作用:一种优化方法

2023 IEEE Information Theory Workshop (ITW) Pub Date : 2023-04-23 DOI: 10.1109/ITW55543.2023.10161662

Christopher Hojny, A. B. Kilic, A. Ravagnani

引用次数: 0

Compressed sensing with ℓ0-norm: statistical physics analysis & algorithms for signal recovery 具有0范数的压缩感知:信号恢复的统计物理分析与算法

2023 IEEE Information Theory Workshop (ITW) Pub Date : 2023-04-23 DOI: 10.1109/ITW55543.2023.10161684

D. Barbier, C. Lucibello, Luca Saglietti, F. Krzakala, L. Zdeborová

{"title":"Compressed sensing with ℓ0-norm: statistical physics analysis & algorithms for signal recovery","authors":"D. Barbier, C. Lucibello, Luca Saglietti, F. Krzakala, L. Zdeborová","doi":"10.1109/ITW55543.2023.10161684","DOIUrl":"https://doi.org/10.1109/ITW55543.2023.10161684","url":null,"abstract":"Noiseless compressive sensing is a protocol that enables undersampling and later recovery of a signal without loss of information. This compression is possible because the signal is usually sufficiently sparse in a given basis. Currently, the algorithm offering the best tradeoff between compression rate, robustness, and speed for compressive sensing is the LASSO (ℓ1-norm bias) algorithm. However, many studies have pointed out the possibility that the implementation of ℓp-norms biases, with p smaller than one, could give better performance while sacrificing convexity. In this work, we focus specifically on the extreme case of the ℓ0-based reconstruction, a task that is complicated by the discontinuity of the loss. In the first part of the paper, we describe via statistical physics methods, and in particular the replica method, how the solutions to this optimization problem are arranged in a clustered structure. We observe two distinct regimes: one at low compression rate where the signal can be recovered exactly, and one at high compression rate where the signal cannot be recovered accurately. In the second part, we present two message-passing algorithms based on our first results for the ℓ0-norm optimization problem. The proposed algorithms are able to recover the signal at compression rates higher than the ones achieved by LASSO while being computationally efficient.","PeriodicalId":439800,"journal":{"name":"2023 IEEE Information Theory Workshop (ITW)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121558899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deterministic K-Identification For Slow Fading Channels 慢衰落信道的确定性k辨识

2023 IEEE Information Theory Workshop (ITW) Pub Date : 2023-04-23 DOI: 10.1109/ITW55543.2023.10161643

Muris Spahovic, M. J. Salariseddigh, C. Deppe

引用次数: 0

Hyperbolic Sets in Incomplete Tables 不完备表中的双曲集

2023 IEEE Information Theory Workshop (ITW) Pub Date : 2023-04-23 DOI: 10.1109/ITW55543.2023.10161663

J. J. Bernal, J. Simón

引用次数: 0

On the State Estimation Error of "Beam-Pointing" Channels: The Binary Case “波束指向”信道的状态估计误差:二进制情况

2023 IEEE Information Theory Workshop (ITW) Pub Date : 2023-04-23 DOI: 10.1109/ITW55543.2023.10161660

Siyao Li, G. Caire

{"title":"On the State Estimation Error of \"Beam-Pointing\" Channels: The Binary Case","authors":"Siyao Li, G. Caire","doi":"10.1109/ITW55543.2023.10161660","DOIUrl":"https://doi.org/10.1109/ITW55543.2023.10161660","url":null,"abstract":"Sensing capabilities as an integral part of the network have been identified as a novel feature of sixth-generation (6G) wireless networks. As a key driver, millimeter-wave (mmWave) communication largely boosts speed, capacities, and connectivity. In order to maximize the potential of mmWave communication, precise and fast beam acquisition (BA) is crucial, since it compensates for a high pathloss and provides a large beamforming gain. Practically, the angle-of-departure (AoD) remains almost constant over numerous consecutive time slots, the backscatter signal experiences some delay, and the hardware is restricted under the peak power constraint. This work captures these main features by a simple binary beam-pointing (BBP) channel model with in-block memory (iBM) [1], peak cost constraint, and one unit-delayed feedback. In particular, we focus on the sensing capabilities of such a model and characterize the performance of the BA process in terms of the Hamming distortion of the estimated channel state. We encode the position of the AoD and derive the minimum distortion of the BBP channel under the peak cost constraint with no communication constraint. Our previous work [2] proposed a joint communication and sensing (JCAS) algorithm, which achieves the capacity of the same channel model. Herein, we show that by employing this JCAS transmission strategy, optimal data communication and channel estimation can be accomplished simultaneously. This yields the complete characterization of the capacity-distortion tradeoff for this model.","PeriodicalId":439800,"journal":{"name":"2023 IEEE Information Theory Workshop (ITW)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125257144","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Generic Decoding in the Cover Metric 覆盖度量中的通用解码

2023 IEEE Information Theory Workshop (ITW) Pub Date : 2023-04-23 DOI: 10.1109/ITW55543.2023.10160246

Sebastian Bitzer, Julian Renner, A. Wachter-Zeh, Violetta Weger

引用次数: 0

Generalization Properties of Adversarial Training for -ℓ0 Bounded Adversarial Attacks - l0有界对抗性攻击对抗训练的泛化性质

2023 IEEE Information Theory Workshop (ITW) Pub Date : 2023-04-23 DOI: 10.1109/ITW55543.2023.10161648

Payam Delgosha, Hamed Hassani, Ramtin Pedarsani

引用次数: 0

State Estimation Entropy for Two-State Markov Sources in Slotted ALOHA Random Access Channels 开槽ALOHA随机接入信道中两态马尔可夫源的状态估计熵

2023 IEEE Information Theory Workshop (ITW) Pub Date : 2023-04-23 DOI: 10.1109/ITW55543.2023.10161627

G. Cocco, A. Munari, G. Liva

引用次数: 2

A Combinatorial Proof for the Dowry Problem 嫁妆问题的一个组合证明

2023 IEEE Information Theory Workshop (ITW) Pub Date : 2023-04-23 DOI: 10.1109/ITW55543.2023.10161638

Xujun Liu, O. Milenkovic, G. Moustakides

引用次数: 0